Cognitive adaptations for well-being management

Abstract

Disclosed aspects relate to cognitive adaptations for well-being management in a living environment. A set of sensor-derived data for the living environment may be ingested. The ingestion of a set of sensor-derived data may occur using a set of micro-cognitive modules. The set of sensor-derived data may be analyzed using a machine learning technique. The set of sensor-derived data may be analyzed to detect an anomalous event related to the living environment. The anomalous event may be detected based on the set of sensor-derived data. An anomalous event response action may be performed in response to detecting the anomalous event.

what is claimed is: 
     
         1 . A computer-implemented method of cognitive adaptations for well-being management in a living environment, the method comprising:
 ingesting, using a set of micro-cognitive modules, a set of sensor-derived data for the living environment;   analyzing, using a machine learning technique, the set of sensor-derived data to detect an anomalous event related to the living environment;   detecting, based on the set of sensor-derived data, the anomalous event; and   performing, in response to detecting the anomalous event, an anomalous event response action.   
     
     
         2 . The method of  claim 1 , further comprising:
 generating, with respect to an individual, a set of individualized sensor-derived norms based on the set of sensor-derived data;   receiving, with respect to the individual, a new sensor-derived data entry;   carrying-out a comparison of the new sensor-derived data entry with the set of individualized sensor-derived norms to identify a non-normative event; and   identifying, based on the comparison achieving a threshold distinction, the non-normative event which indicates the anomalous event.   
     
     
         3 . The method of  claim 1 , further comprising:
 providing, to perform the anomalous event response action, a notification which indicates the anomalous event.   
     
     
         4 . The method of  claim 1 , further comprising:
 constructing a respective micro-cognitive module of the set of micro-cognitive modules to manage a respective element of the set of sensor-derived data.   
     
     
         5 . The method of  claim 4 , further comprising:
 configuring the respective element of the set of sensor-derived data to include a single isolated sensor-derived data parameter.   
     
     
         6 . The method of  claim 4 , further comprising:
 structuring the respective micro-cognitive module to include:
 a data storage unit, 
 a cognitive analytics module, 
 an event generator, and 
 an event handler. 
   
     
     
         7 . The method of  claim 1 , further comprising:
 receiving, by the set of micro-cognitive modules, a set of sensor-collected data; and   ingesting, by a well-being engine in response to the ingesting using the set of micro-cognitive modules, the set of sensor-derived data.   
     
     
         8 . The method of  claim 1 , further comprising:
 configuring the set of micro-cognitive modules to operate as a set of analysis tools to examine, in isolation, a single element of a measurable behavior of an individual.   
     
     
         9 . The method of  claim 8 , further comprising:
 configuring the set of micro-cognitive modules to self-learn, to identify a set of behavior patterns of an individual, and to trigger an alarm parameter in response to a pattern mismatch.   
     
     
         10 . The method of  claim 9 , further comprising:
 compiling, by a well-being engine, the set of sensor-derived data from the set of micro-cognitive modules, wherein the set of sensor-derived data is in an integrated form in response to the compiling.   
     
     
         11 . The method of  claim 10 , further comprising:
 determining, using a predetermined criterion, a nature of the anomalous event.   
     
     
         12 . The method of  claim 11 , further comprising:
 performing, based on the nature of the anomalous event, the anomalous event response action.   
     
     
         13 . The method of  claim 1 , further comprising:
 achieving, to trigger detection of the anomalous event, a confidence factor with respect to the set of sensor-derived data.   
     
     
         14 . The method of  claim 1 , further comprising:
 ascertaining, using the machine learning technique, a set of behavior patterns with respect to an individual;   receiving, with respect to the individual, a new sensor-derived data entry;   evaluating the new sensor-derived data entry with respect to the set of behavior patterns; and   resolving that the new sensor-derived data entry exceeds a threshold difference with respect to the set of behavior patterns.   
     
     
         15 . The method of  claim 1 , wherein the ingesting, the analyzing, the detecting, and the performing each occur in a dynamic fashion to streamline well-being management. 
     
     
         16 . The method of  claim 1 , wherein the ingesting, the analyzing, the detecting, and the performing each occur in an automated fashion without user intervention. 
     
     
         17 . The method of  claim 2 , further comprising:
 constructing a respective micro-cognitive module of the set of micro-cognitive modules to manage a respective element of the set of sensor-derived data;   structuring the respective micro-cognitive module to include:
 a data storage unit, 
 a cognitive analytics module, 
 an event generator, and 
 an event handler; 
   configuring the respective element of the set of sensor-derived data to include a single isolated sensor-derived data parameter;   receiving, by the set of micro-cognitive modules, a set of sensor-collected data;   ingesting, by a well-being engine in response to the ingesting using the set of micro-cognitive modules, the set of sensor-derived data;   achieving, to trigger detection of the anomalous event, a confidence factor with respect to the set of sensor-derived data; and   providing, to perform the anomalous event response action, a notification which indicates the anomalous event.